Papers with Code 아카이브
3D Reconstruction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 10
- 보존된 평가 기록
- 44
3D Reconstruction is the task of creating a 3D model or representation of an object or scene from 2D images or other data sources. The goal of 3D reconstruction is to create a virtual representation of an object or scene that can be used for a variety of purposes, such as visualization, animation, simulation, and analysis. It can be used in fields such as computer vision, robotics, and virtual reality.
Image: Gwak et al
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/luigifreda/plvs
공식 코드PLVS: A SLAM System with Points, Lines, Volumetric Mapping, and 3D Incremental Segmentation
https://github.com/lukemelas/projection-conditioned-point-cloud-diffusion
공식 코드$PC^2$: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction
https://github.com/lusxvr/dcseg
공식 코드DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian Splatting
https://github.com/lxq1000/dfa-instruct
공식 코드https://github.com/lym29/EasyHOI
공식 코드https://github.com/lyndonzheng/Free3D
공식 코드Free3D: Consistent Novel View Synthesis without 3D Representation
https://github.com/lzhengchun/BraggNN
공식 코드https://github.com/lzqsd/TransparentShapeReconstruction
공식 코드Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes
https://github.com/lzx551402/ASLFeat
공식 코드ASLFeat: Learning Local Features of Accurate Shape and Localization
https://github.com/m3dv/impulse
공식 코드What Makes for Automatic Reconstruction of Pulmonary Segments
https://github.com/machineperceptionlab/cq-nir
공식 코드Coordinate Quantized Neural Implicit Representations for Multi-view Reconstruction
https://github.com/maeyounes/SparseCraft
공식 코드SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearization
https://github.com/magnet300/camme
공식 코드CAMME: Adaptive Deepfake Image Detection with Multi-Modal Cross-Attention
https://github.com/mameratrujillo/Efficient_Scene_Compression
공식 코드https://github.com/manycore-research/PlankAssembly
공식 코드PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs
https://github.com/manyilee/plada
공식 코드https://github.com/mapooon/selfblendedimages
공식 코드https://github.com/marcelampc/d3net_depth_estimation
공식 코드Deep Depth from Defocus: how can defocus blur improve 3D estimation using dense neural networks?
https://github.com/marrlab/shapr_torch
공식 코드Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstruction
https://github.com/masterhow/e-3dgs
공식 코드https://github.com/masterhow/occfiner
공식 코드Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving
https://github.com/mattgroh/cognitive-science-detecting-deepfakes
공식 코드Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowds
https://github.com/mattwallingford/360-1m
공식 코드From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos
https://github.com/maturk/dn-splatter
공식 코드DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing
https://github.com/maybelx/mvsformerplusplus
공식 코드MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
https://github.com/med-air/endonerf
공식 코드Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgery
https://github.com/megvii-research/AAAI2023-PVD
공식 코드https://github.com/megvii-research/caddm
공식 코드Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
https://github.com/megvii-research/fst-matching
공식 코드https://github.com/megvii-research/occdepth
공식 코드OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
https://github.com/megviirobot/transmvsnet
공식 코드TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers
https://github.com/menggerSherry/Trans_Fusion_Net
공식 코드https://github.com/mercerai/evggs
공식 코드EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting
https://github.com/mhayoz/online_endo_track
공식 코드Online 3D reconstruction and dense tracking in endoscopic videos
https://github.com/mihaidusmanu/d2-net
공식 코드D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.